Predictive Demand Response Modeling for Logistic Systems Innovation and Optimization

Abstract

In the ever-increasing dynamics of global business markets, logistic systems must optimize the usage of all possible sources to continually innovate. Scenario-based demand prediction plays an important role in the effective economic operations and planning of logistics. However, many uncertainties and demand variability, which are associated with innovative changes, complicate demand forecasting and expose system operators to the risk of failing to meet demand. This dissertation presents new approaches to predictively explore how customer preferences will change and consequently demand would respond to the new setup of services caused by an innovative transformation of the logistic layout. The critical challenge is that the responses from customers in particular and demand in general to the innovative changes and corresponding adjustments are uncertain and unknown in practice, and there is no historical data to learn from and directly support the predictive model. In this dissertation, we are dealing with three different predictive demand response modeling approaches, jointly shaping a new methodological pathway. Chapter 1 provides a novel approach for predictive modeling probabilistic customer behavior over new service offers which are much faster than ever done before, based on the case of a large Chinese parcel-delivery service provider. Chapter 2 introduces an approach for predicting scenario-based erection-site demand schedules under uncertainty of disruptive events in construction projects whose logistics transformed from traditional to modular style, based on the case of a USA-based innovative leader in modular building production. For such a leader to advance in its logistics design innovations and associated capacity adjustments, and also to enhance its capability for taking more market share, it is crucial to estimate potential future demand for modular construction and corresponding probable projects in terms of their potential location, size, and characteristics. For this purpose, Chapter 3 introduces a methodological approach for estimating scenario-based future demand for modular construction projects to be implemented over the US metropolitan statistical areas.